Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9785
    Prev
    Next
    INDEX
    Explanations

    references to the month of August

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rè
    -0.74
    :+:
    -0.65
    #+#
    -0.60
    pade
    -0.57
    jsii
    -0.57
    principalTable
    -0.57
     />\
    -0.57
    Бли
    -0.56
    irait
    -0.56
     Mors
    -0.56
    POSITIVE LOGITS
    ConstraintMaker
    0.77
    ftagPool
    0.70
     geleverd
    0.61
    LookAnd
    0.60
     admiten
    0.60
     grecque
    0.59
     intérieure
    0.58
     nhiên
    0.58
     dieťa
    0.58
     igång
    0.58
    Activations Density 0.102%

    No Known Activations